Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1285 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3226. Min Range: -1.3226

Max Act: 1.3226. Min Act: -0.0001

Data Index: 1473050 (Python Code)

Max Activating Token Index: 186

Text #1

Max Range: 1.3226. Min Range: -1.3226

Max Act: 1.2702. Min Act: -0.0000

Data Index: 799519 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 1.3226. Min Range: -1.3226

Max Act: 1.2189. Min Act: -0.0001

Data Index: 1159721 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 1.3226. Min Range: -1.3226

Max Act: 1.0988. Min Act: -0.0001

Data Index: 1384894 (Python Code)

Max Activating Token Index: 240

Text #4

Max Range: 1.3226. Min Range: -1.3226

Max Act: 1.0340. Min Act: -0.0001

Data Index: 284887 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 1.3226. Min Range: -1.3226

Max Act: 1.1167. Min Act: -0.0000

Data Index: 847131 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 1.3226. Min Range: -1.3226

Max Act: 1.0546. Min Act: -0.0001

Data Index: 1060898 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 1.3226. Min Range: -1.3226

Max Act: 1.1625. Min Act: -0.0001

Data Index: 413447 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 1.3226. Min Range: -1.3226

Max Act: 1.0513. Min Act: -0.0001

Data Index: 1436365 (Python Code)

Max Activating Token Index: 365

Text #9

Max Range: 1.3226. Min Range: -1.3226

Max Act: 0.9620. Min Act: -0.0001

Data Index: 268134 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 1.3226. Min Range: -1.3226

Max Act: 0.9328. Min Act: -0.0001

Data Index: 1459947 (Python Code)

Max Activating Token Index: 679

Text #11

Max Range: 1.3226. Min Range: -1.3226

Max Act: 0.8974. Min Act: -0.0001

Data Index: 1527628 (Python Code)

Max Activating Token Index: 723

Text #12

Max Range: 1.3226. Min Range: -1.3226

Max Act: 0.8708. Min Act: -0.0001

Data Index: 62736 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 1.3226. Min Range: -1.3226

Max Act: 0.8908. Min Act: -0.0001

Data Index: 885248 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 1.3226. Min Range: -1.3226

Max Act: 0.8936. Min Act: -0.0000

Data Index: 290963 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 1.3226. Min Range: -1.3226

Max Act: 0.9420. Min Act: -0.0001

Data Index: 1329507 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 1.3226. Min Range: -1.3226

Max Act: 0.8835. Min Act: -0.0001

Data Index: 329128 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 1.3226. Min Range: -1.3226

Max Act: 0.8780. Min Act: -0.0001

Data Index: 611778 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 1.3226. Min Range: -1.3226

Max Act: 0.9042. Min Act: -0.0001

Data Index: 340748 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 1.3226. Min Range: -1.3226

Max Act: 0.8446. Min Act: -0.0001

Data Index: 956757 (C4 (Web Text))

Max Activating Token Index: 635